combined_args.json

{
    "use_picard": false,
    "launch_picard": false,
    "picard_host": "localhost",
    "picard_port": 9090,
    "picard_mode": "parse_with_guards",
    "picard_schedule": "incremental",
    "picard_max_tokens_to_check": 2,
    "model_name_or_path": "t5-small",
    "config_name": null,
    "tokenizer_name": null,
    "cache_dir": "~/picard/transformers_cache",
    "use_fast_tokenizer": true,
    "model_revision": "main",
    "use_auth_token": false,
    "dataset": "spider",
    "dataset_paths": {
        "spider": "./seq2seq/datasets/spider",
        "cosql": "./seq2seq/datasets/cosql",
        "spider_realistic": "./seq2seq/datasets/spider_realistic",
        "spider_syn": "./seq2seq/datasets/spider_syn",
        "spider_dk": "./seq2seq/datasets/spider_dk"
    },
    "metric_config": "both",
    "metric_paths": {
        "spider": "./seq2seq/metrics/spider",
        "spider_realistic": "./seq2seq/metrics/spider",
        "cosql": "./seq2seq/metrics/cosql",
        "spider_syn": "./seq2seq/metrics/spider",
        "spider_dk": "./seq2seq/metrics/spider"
    },
    "test_suite_db_dir": null,
    "data_config_file": null,
    "test_sections": null,
    "overwrite_cache": false,
    "preprocessing_num_workers": null,
    "max_source_length": 512,
    "max_target_length": 512,
    "val_max_target_length": 512,
    "val_max_time": null,
    "max_train_samples": null,
    "max_val_samples": null,
    "num_beams": 1,
    "num_beam_groups": 1,
    "diversity_penalty": null,
    "num_return_sequences": null,
    "ignore_pad_token_for_loss": true,
    "source_prefix": "",
    "schema_serialization_type": "peteshaw",
    "schema_serialization_randomized": false,
    "schema_serialization_with_db_id": true,
    "schema_serialization_with_db_content": true,
    "normalize_query": true,
    "target_with_db_id": true,
    "output_dir": "/home/jining/picard/train",
    "overwrite_output_dir": true,
    "do_train": true,
    "do_eval": true,
    "do_predict": false,
    "evaluation_strategy": "steps",
    "prediction_loss_only": false,
    "per_device_train_batch_size": 8,
    "per_device_eval_batch_size": 8,
    "per_gpu_train_batch_size": "None",
    "per_gpu_eval_batch_size": "None",
    "gradient_accumulation_steps": 8,
    "eval_accumulation_steps": "None",
    "eval_delay": 0,
    "learning_rate": 0.0001,
    "weight_decay": 0.0,
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "max_grad_norm": 1.0,
    "num_train_epochs": 10,
    "max_steps": -1,
    "lr_scheduler_type": "constant",
    "warmup_ratio": 0.0,
    "warmup_steps": 0,
    "log_level": -1,
    "log_level_replica": -1,
    "log_on_each_node": true,
    "logging_dir": "/home/jining/picard/train/runs/Jul26_15-25-41_icu-gpu-4.sl.cloud9.ibm.com",
    "logging_strategy": "steps",
    "logging_first_step": false,
    "logging_steps": 40000,
    "logging_nan_inf_filter": true,
    "save_strategy": "steps",
    "save_steps": 64000,
    "save_total_limit": 128,
    "save_on_each_node": false,
    "no_cuda": false,
    "seed": 1,
    "data_seed": "None",
    "jit_mode_eval": false,
    "use_ipex": false,
    "bf16": false,
    "fp16": false,
    "fp16_opt_level": "O1",
    "half_precision_backend": "auto",
    "bf16_full_eval": false,
    "fp16_full_eval": false,
    "tf32": "None",
    "xpu_backend": "None",
    "tpu_num_cores": "None",
    "tpu_metrics_debug": false,
    "debug": "[]",
    "dataloader_drop_last": false,
    "eval_steps": 64000,
    "dataloader_num_workers": 0,
    "past_index": -1,
    "run_name": "t5-spider",
    "disable_tqdm": false,
    "remove_unused_columns": true,
    "label_names": "None",
    "load_best_model_at_end": false,
    "metric_for_best_model": "exact_match",
    "greater_is_better": true,
    "ignore_data_skip": false,
    "sharded_ddp": "[]",
    "fsdp": "[]",
    "fsdp_min_num_params": 0,
    "deepspeed": "None",
    "label_smoothing_factor": 0.0,
    "optim": "adafactor",
    "adafactor": true,
    "group_by_length": false,
    "length_column_name": "length",
    "report_to": "['tensorboard']",
    "ddp_find_unused_parameters": "None",
    "ddp_bucket_cap_mb": "None",
    "dataloader_pin_memory": true,
    "skip_memory_metrics": true,
    "use_legacy_prediction_loop": false,
    "push_to_hub": false,
    "resume_from_checkpoint": "None",
    "hub_model_id": "None",
    "hub_strategy": "every_save",
    "hub_token": "<HUB_TOKEN>",
    "hub_private_repo": false,
    "gradient_checkpointing": false,
    "include_inputs_for_metrics": false,
    "fp16_backend": "auto",
    "push_to_hub_model_id": "None",
    "push_to_hub_organization": "None",
    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
    "_n_gpu": 2,
    "mp_parameters": "",
    "auto_find_batch_size": false,
    "full_determinism": false,
    "torchdynamo": "None",
    "ray_scope": "last",
    "sortish_sampler": false,
    "predict_with_generate": true,
    "generation_max_length": "None",
    "generation_num_beams": "None",
    "train_batch_size": 16,
    "eval_batch_size": 16
}